May 21, 2021
I’ve released a new > Github repository <, > dataset <, and > ArXiv preprint < for a paper I submitted to a journal, titled “BodyPressure – Inferring Body Pose and Contact Pressure from a Depth Image.” It shows that a low-cost camera might be used to identify peak pressure regions on a person in bed, which is applicable to the problem of preventing pressure injuries in a healthcare setting. I also filed a provisional patent for it, so if you are interested in commercializing it, please contact me. Here is the abstract:
Contact pressure between the human body and its surroundings has important implications. For example, it plays a role in comfort, safety, posture, and health. We present a method that infers contact pressure between a human body and a mattress from a depth image. Specifically, we focus on using a depth image from a downward facing camera to infer pressure on a body at rest in bed occluded by bedding, which is directly applicable to the prevention of pressure injuries in healthcare. Our approach involves augmenting a real dataset with synthetic data generated via a soft-body physics simulation of a human body, a mattress, a pressure sensing mat, and a blanket. We introduce a novel deep network that we trained on an augmented dataset and evaluated with real data. The network contains an embedded human body mesh model and uses a white-box model of depth and pressure image generation. Our network successfully infers body pose, outperforming prior work. It also infers contact pressure across a 3D mesh model of the human body, which is a novel capability, and does so in the presence of occlusion from blankets.
February 24, 2020
I’m very happy to share that my paper, “Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image Using Synthetic Data” was accepted at CVPR 2020. Here is the abstract:
People spend a substantial part of life at rest in bed. 3D human pose and shape estimation for this activity would have numerous beneficial applications, yet line-of-sight perception is complicated by occlusion from bedding. Pressure sensing mats are a promising alternative, but training data is challenging to collect at scale. We describe a physics-based method that simulates human bodies at rest in a bed with a pressure sensing mat, and present PressurePose, a synthetic dataset with 206K pressure images with 3D human poses and shapes. We also present PressureNet, a deep learning model that estimates human pose and shape from a pressure image and a measured height and weight. PressureNet has a model of pressure image generation to promote consistency between estimated 3D body models and pressure image input. In our evaluations, PressureNet performed well with real data from participants in diverse poses, even though it had only been trained with synthetic data, and PressureNet’s performance degraded when we ablated its model of pressure image generation.